Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges

TL;DR

This paper explores how embedded software engineering teams are adopting generative AI, highlighting emerging practices and challenges in integrating AI into safety-critical, resource-constrained environments.

Contribution

It provides qualitative insights from experts on new workflows, governance, and challenges in implementing AI-augmented development in embedded systems.

Findings

Identified 11 emerging practices for AI integration.

Outlined 14 key challenges in AI adoption for embedded software.

Revealed changes in workflows, roles, and toolchains.

Abstract

A new transformation is underway in software engineering, driven by the rapid adoption of generative AI in development workflows. Similar to how version control systems once automated manual coordination, AI tools are now beginning to automate many aspects of programming. For embedded software engineering organizations, however, this marks their first experience integrating AI into safety-critical and resource-constrained environments. The strict demands for determinism, reliability, and traceability pose unique challenges for adopting generative technologies. In this paper, we present findings from a qualitative study with ten senior experts from four companies who are evaluating generative AI-augmented development for embedded software. Through semi-structured focus group interviews and structured brainstorming sessions, we identified eleven emerging practices and fourteen challenges related to the orchestration, responsible governance, and sustainable adoption of generative AI tools. Our results show how embedded software engineering teams are rethinking workflows, roles, and toolchains to enable a sustainable transition toward agentic pipelines and generative AI-augmented development.